The Orchestrator › Models › Reka
Reka: Reka Edge
Reka Edge is an extremely efficient 7B multimodal vision-language model that accepts image/video+text inputs and generates text outputs. This model is optimized specifically to deliver industry-leading performance in image understanding,...
Specifications
| Provider | Reka |
| Model ID | rekaai/reka-edge |
| Context window | 16K tokens (16,384) |
| Modalities | text + image + video → text |
| Tokenizer | Other |
| Router sources | OpenRouter |
| Released | 2026-03-20 |
| Tracked since | 2026-11-14 |
| Popularity | Not in the ranked set |
| Reasoning | Supported |
Pricing (per million tokens)
| Variant | Source | API ID | Input | Output | Context |
|---|---|---|---|---|---|
| standard | OpenRouter | rekaai/reka-edge | $0.1 | $0.1 | 16K |
Recorded price history
| Date | Input / 1M | Output / 1M | Context |
|---|---|---|---|
| 2026-11-14 | $0.1 | $0.1 | 16K |
Capabilities
Vision (image input)Video inputAgentic tool useStructured outputs
Supported parameters
frequency_penalty, logprobs, max_tokens, presence_penalty, seed, stop, structured_outputs, temperature, tool_choice, tools, top_k, top_logprobs, top_p